mlsanityData to 14 Oct 2026

ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation

arXiv 2104.09136 ↗First posted 19 Apr 2021cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain. Several SSDA methods have been proposed recently, which however fail to fully exploit the value of the few labeled target samples. In this paper, we propose Enhanced Categorical Alignment and Consistency Learning (ECACL), a holistic SSDA framework that incorporates multiple mutually complementary domain alignment techniques. ECACL includes two categorical domain alignment techniques that achieve class-level alignment, a strong data augmentation based technique that enhances the model's generalizability and a consistency learning based technique that forces the model to be robust with image perturbations. These techniques are applied on one or multiple of the three inputs (labeled source, unlabeled target, and labeled target) and align the domains from different perspectives. ECACL unifies them together and achieves fairly comprehensive domain alignments that are much better than the existing methods: For example, ECACL raises the state-of-the-art accuracy from 68.4 to 81.1 on VisDA2017 and from 45.5 to 53.4 on DomainNet for the 1-shot setting. Our code is available at urlhttps://github.com/kailigo/pacl.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 35 of its 55 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

35 of 55 references.

References · 35

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  9. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  10. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  12. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
23 more
  1. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  2. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  3. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  4. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  5. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  6. 2019Confidence Regularized Self-Trainingcited by 419
  7. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  8. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  9. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  10. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  11. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  12. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  13. 2017Adversarial Dropout Regularizationcited by 106
  14. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 86
  15. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  16. 2017AutoDIAL: Automatic DomaIn Alignment Layerscited by 75
  17. 2020Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptationcited by 69
  18. 2020Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptationcited by 64
  19. 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
  20. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  21. 2019d-SNE: Domain Adaptation using Stochastic Neighborhood Embeddingcited by 40
  22. 2020Cross-Domain Document Object Detection: Benchmark Suite and Methodcited by 24
  23. 2019A simple baseline for domain adaptation using rotation predictioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 8; 2024: 7; 2025: 3; 2026: 1.

31 papers.

Sort:

  1. 2022ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixingcited by 28
  2. 2022Multi-level Consistency Learning for Semi-supervised Domain Adaptationcited by 20
  3. 2022Learning Distinctive Margin toward Active Domain Adaptationcited by 18
  4. 2023Consistency Regularization for Generalizable Source-free Domain Adaptationcited by 17
  5. 2022Combating Label Distribution Shift for Active Domain Adaptationcited by 14
  6. 2023Making Reconstruction-based Method Great Again for Video Anomaly Detectioncited by 10
  7. 2023Semi-supervised Domain Adaptation via Prototype-based Multi-level Learningcited by 9
  8. 2024Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptationcited by 9
  9. 2021Unsupervised Domain Adaptation for Constraining Star Formation Historiescited by 8
  10. 2021Probabilistic Contrastive Learning for Domain Adaptationcited by 7
  11. 2021Learning Domain Invariant Representations by Joint Wasserstein Distance Minimizationcited by 6
  12. 2022Low-confidence Samples Matter for Domain Adaptationcited by 4
19 more
  1. 2022Local Context-Aware Active Domain Adaptationcited by 4
  2. 2023Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropycited by 4
  3. 2024Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Biascited by 3
  4. 2022Domain-Augmented Domain Adaptationcited by 2
  5. 2024Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptationcited by 2
  6. 2023Multi-Domain Learning From Insufficient Annotationscited by 1
  7. 2023Universal Semi-supervised Model Adaptation via Collaborative Consistency Trainingcited by 1
  8. 2023Dual-level Interaction for Domain Adaptive Semantic Segmentationcited by 1
  9. 2024AdaEmbed: Semi-supervised Domain Adaptation in the Embedding Spacecited by 1
  10. 2024Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptationcited by 1
  11. 2024Semi-Supervised Transfer Boosting (SS-TrBoosting)cited by 1
  12. 2025Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentationcited by 1
  13. 2022Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labelingcited by 0
  14. 2022Pred&Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptationcited by 0
  15. 2023Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-Supervised Domain Adaptationcited by 0
  16. 2024Progressive Multi-Level Alignments for Semi-Supervised Domain Adaptation SAR Target Recognition Using Simulated Datacited by 0
  17. 2025Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptationcited by 0
  18. 2025MoSSDA: A Semi-Supervised Domain Adaptation Framework for Multivariate Time-Series Classification using Momentum Encodercited by 0
  19. 2026Ranking-Guided Semi-Supervised Domain Adaptation for Severity Classificationcited by 0